patchman AGENTS.md

Security-review guidance for Patchman, a defensive repository for finding software security problems. It defines read-only review behavior, severity and confidence ranking, safe reporting, and the main areas to inspect.

In plain words
What is it for?
Use it to review access control, authentication, tenant isolation, business rules, input handling, server-side requests, secret exposure, logging, and database access.
Why use it?
It keeps reviews focused on authorized defensive work and helps distinguish high-impact, well-supported findings from speculation.

Instructions file for CodexOpenCode

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

agentmods
npx agentmods add instructions/muhammedzohaib/patchman/agents-md
Clone the repo
git clone --depth 1 https://github.com/MuhammedZohaib/patchman

Made for: Codex, OpenCode.

Per session 132 This file is loaded in full into every session.
When invoked 132 The same file — it is already loaded in full.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5 $0.00132 $0.00132
Opus 5 $0.00066 $0.00066
Sonnet 5 $0.00026 $0.00026
Haiku 4.5 $0.00013 $0.00013

Measured 2d ago against content hash 0e759dc7b2d5, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

patchman AGENTS.md scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

AGENTS.md · 22 lines

What it actually says

AGENTS.md

Patchman is a defensive security review repository.

Agent expectations:

  • Default to read-only review behavior.
  • Ask for missing authorization or deployment context when needed.
  • Rank findings by severity and confidence.
  • Use the Patchman findings format.
  • Refuse offensive, evasive, or destructive requests.
  • Prefer minimal safe patch guidance over speculative redesign.

Review priorities:

  1. Broken access control and tenant isolation
  2. Authentication, session, and reset flows
  3. Business logic abuse paths
  4. Dangerous input handling and server-side fetch behavior
  5. Secret exposure and unsafe logging
  6. ORM misuse and data-access regressions
Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 2d ago First seen · 22 lines · 132 tokens per session scan A 0e759dc7b2d5

Subscribe to this mod's changes

patchman AGENTS.md is an instructions file published in the GitHub repository MuhammedZohaib/patchman (3 stars, last pushed 4mo ago), licensed MIT. It adds 132 tokens to every session, about $0.0007 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.